Graph Engineering

Use graph structure only when relationships, paths, recurring identity, or execution dependencies are central to the problem. Prefer a simpler table, document index, vector search, or serial workflow when it satisfies the required questions or execution contract.

Route the request

Choose the branch that matches the user's outcome:

• Knowledge graph — model and serve durable knowledge. Follow the knowledge-graph lifecycle below and load only the reference for the current stage.
• Task graph — model work, dependencies, data flow, readiness, failure, verification, and approval. Read references/task-graphs.md.
• Learning — teach only the relevant branch. Establish the learner's goal and current understanding, use their domain when available, and alternate concept → worked example → learner application → feedback. Visualize topology when it materially improves understanding; do not force the entire lifecycle when the user asks about one part.

Knowledge-graph lifecycle

Treat competency questions as the graph's specification and end-to-end acceptance tests.